© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52669
    Prev
    Next
    INDEX
    Explanations

    need to be reminded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    િક
    0.57
    gives
    0.54
    و
    0.53
    ج
    0.47
    します
    0.47
    ب
    0.47
    ある
    0.47
     ނ
    0.46
    jewelry
    0.46
    ଣ
    0.46
    POSITIVE LOGITS
     peaks
    0.55
     seism
    0.45
     marshmallow
    0.43
     clash
    0.41
     jää
    0.40
    ரிக்கை
    0.40
     dots
    0.40
     sampler
    0.39
     remix
    0.39
    ฟรี
    0.39
    Activations Density 0.008%

    No Known Activations